Llama-3.1-8B-Instruct

Name: Llama-3.1-8B-Instruct
Author: Meta Llama

llama3.18B

Context

131K

Max output

131K

Capabilities

Show unsupported (5)

Reasoning & Interaction

Tool Calling

Infrastructure

Streaming

Fine-tuning

Details

ProviderMeta Llama

Creatormeta

FamilyLlama-3.1

Licensellama3.1

Status—

Typechat

Input modalitiestext

Output modalitiestext

Open weightYes

Parameters8B

Architecture—

Context window131K tokens

Max input—

Max output131K tokens

Reasoning tokens—

Knowledge cutoff2023-12

Release date2024-07-18

Sourceofficial

Tools

Function Callingfunction_calling

Call external functions and APIs

Family Comparison: Llama-3.1

Model	Caps	Perf	Speed	Context	Max out
Llama-3.1-405B-Instruct-FP8	TSF	—	—	131K	131K
Llama-3.1-405B-Instruct	TSF	—	—	131K	131K
Llama-3.1-70B-Instruct	TSF	—	—	131K	131K
Llama-3.1-8B-Instruct	TSF	—	—	131K	131K

API

GET/v1/models/meta/Llama-3.1-8B-Instruct

Llama-3.1-8B-Instruct

Changes · 3 entries

Llama-3.1-8B-Instructupdate1cd659eMar 24, 2026, 04:19 AM

capabilitiesfine tuningyes

Llama-3.1-8B-Instructupdate2b100acMar 23, 2026, 05:30 AM

familyLlama-3.1

model_typechat

licensellama3.1

parameters8

page_urlhttps://huggingface.co/meta-llama/Llama-3.1-8B-Instruct

open_weightyes

tools["function_calling"]

release_date2024-07-18

knowledge_cutoff2023-12

max_output_tokens131072

Llama-3.1-8B-Instructcreate7f5c66fMar 21, 2026, 05:16 AM